In order to solve the problem of mining biomedical knowledge, a biomedical semantic-based knowledge discovery method (Bio-SKDM) is proposed. Using the semantic types and semantic relations of the biomedical concepts, Bio-SKDM can identify the relevant concepts collected from Medline and generate the novel hypothesis between these concepts. The experiment result shows that compared with ARROWSMITH and LITLINKER, Bio-SKDM generates less but more relevant novel hypotheses and requires less human intervention in the discovery procedure.
展开▼